Copertina

Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Beier, Wang, Cheng, Wei, Hongxin, Li, Sharon, Du, Xuefeng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
di: Luo, Beier, et al.
Pubblicazione: (2025)

Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
di: Ghaffari, Alireza, et al.
Pubblicazione: (2025)

Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
di: Liu, Taowen, et al.
Pubblicazione: (2025)

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
di: Zhang, Jingxuan, et al.
Pubblicazione: (2026)

Provable Training Data Identification for Large Language Models
di: Liu, Zhenlong, et al.
Pubblicazione: (2025)

Unlocking [CLS] Features for Continual Post-Training
di: Yildirim, Murat Onur, et al.
Pubblicazione: (2025)

Heterogeneous Low-Bandwidth Pre-Training of LLMs
di: Obeidi, Yazan, et al.
Pubblicazione: (2026)

Graph Pre-Training Models Are Strong Anomaly Detectors
di: Cheng, Jiashun, et al.
Pubblicazione: (2024)

DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs
di: Luo, Yingsong, et al.
Pubblicazione: (2024)

Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
di: Nakkiran, Preetum, et al.
Pubblicazione: (2025)

Dual Prototypes for Adaptive Pre-Trained Model in Class-Incremental Learning
di: Xu, Zhiming, et al.
Pubblicazione: (2024)

Post-Training Statistical Calibration for Higher Activation Sparsity
di: Chua, Vui Seng, et al.
Pubblicazione: (2024)

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
di: Hoang, Dung Anh, et al.
Pubblicazione: (2026)

Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs
di: Xu, Zifei, et al.
Pubblicazione: (2024)

Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
di: Zhou, Wenjie, et al.
Pubblicazione: (2026)

DBellQuant: Breaking the Bell with Double-Bell Transformation for LLMs Post Training Binarization
di: Ye, Zijian, et al.
Pubblicazione: (2025)

Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning
di: Zhou, Da-Wei, et al.
Pubblicazione: (2024)

Self-Supervised Pre-Training for Precipitation Post-Processor
di: An, Sojung, et al.
Pubblicazione: (2023)

LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
di: Chang, Ching, et al.
Pubblicazione: (2023)

The Coverage Principle: How Pre-Training Enables Post-Training
di: Chen, Fan, et al.
Pubblicazione: (2025)

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
di: Nepal, Aadim, et al.
Pubblicazione: (2025)

Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models
di: Hoang, Dung Anh, et al.
Pubblicazione: (2025)

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
di: Liu, Xuewen, et al.
Pubblicazione: (2024)

Unlocking the Potential of Model Calibration in Federated Learning
di: Chu, Yun-Wei, et al.
Pubblicazione: (2024)

CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs
di: Wang, Haoyu, et al.
Pubblicazione: (2024)

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
di: Huang, Wei, et al.
Pubblicazione: (2024)

Mixture-of-Channels: Exploiting Sparse FFNs for Efficient LLMs Pre-Training and Inference
di: Wu, Tong, et al.
Pubblicazione: (2025)

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
di: Lyngkhoi, R E Zera Marveen, et al.
Pubblicazione: (2026)

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training
di: Wang, Yixuan, et al.
Pubblicazione: (2024)

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
di: Xing, Yue, et al.
Pubblicazione: (2024)

Achieving binary weight and activation for LLMs using Post-Training Quantization
di: Song, Siqing, et al.
Pubblicazione: (2025)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
di: Yu, Peiqi, et al.
Pubblicazione: (2026)

HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters
di: Mo, Yujie, et al.
Pubblicazione: (2024)

Open-Vocabulary Calibration for Fine-tuned CLIP
di: Wang, Shuoyuan, et al.
Pubblicazione: (2024)

D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
di: Yan, Xianglong, et al.
Pubblicazione: (2026)

Leveraging RAG for Training-Free Alignment of LLMs
di: Halloran, John T.
Pubblicazione: (2026)

Convex Dataset Valuation for Post-Training
di: Zeng, Siqi, et al.
Pubblicazione: (2026)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
di: Javanmard, Adel, et al.
Pubblicazione: (2026)

Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training
di: Gui, Shurui, et al.
Pubblicazione: (2025)

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
di: Zhang, Jiawei, et al.
Pubblicazione: (2025)